Skip to main content
Glama
Sign In
DeskPilot

DeskPilot

by iamtahiralvi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

act

Runs ordered mouse and keyboard steps on a chosen display, then reports what changed on screen.

Instructions

Run steps in order with the real mouse/keyboard, then return what changed on screen. Target = ref "e12", visible text "Sign in", or [x,y] pixels of the last screenshot. Steps: {"click":T} {"dblclick":T} {"rclick":T} {"hover":T} {"type":"text","into":T?,"clear":bool?,"enter":bool?} {"key":"ctrl+l"|"enter"|"win+e"...,"repeat":n?} {"key_down":"shift"} {"key_up":"shift"} {"scroll":"down|up|left|right","amount":5,"at":T?} {"drag":T,"to":T} {"wait":"text","timeout":10,"gone":bool?} {"sleep":1} {"focus":"w3|title"} {"launch":"app|url"}. Sensitive steps may ask the user first.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "steps": "<steps>"
    },
    "name": "act"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsYes
observeNodiff

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full burden and it does add real context: actions hit the real mouse/keyboard, the tool reports what changed on screen, and sensitive steps may trigger a user confirmation prompt. What is missing is equally significant for a mutation-capable tool — no mention of required foreground window/session state, failure or timeout behavior, or whether partial execution leaves the UI in a modified state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first sentence, then the step grammar is presented as a compact structured list rather than prose. The terse notation earns its space, though shorthands like 'focus:"w3|title"' and 'launch:"app|url"' are cryptic enough to cost a little clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool this complex with no annotations and no output schema, the description covers the action surface well but leaves the return-value semantics of 'observe' and the prerequisites (active window, session state, error handling) undocumented. An agent knows how to compose steps but not fully what it will get back or what happens when a step fails mid-sequence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it largely does: the target forms (ref 'e12', visible text, or [x,y] pixels of the last screenshot) and the full step vocabulary with per-step fields (type/into/clear/enter, key/repeat, scroll amount/at, wait timeout/gone) are spelled out. The exception is the 'observe' parameter (diff/full/none, default diff), which is never explained beyond the implicit hint in 'return what changed on screen'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a concrete verb+resource: 'Run steps in order with the real mouse/keyboard, then return what changed on screen.' That distinguishes it from read-only siblings like screenshot, find, and screen_info, and the phrase 'real mouse/keyboard' signals actual OS-level input rather than synthetic evaluation. It stops short of naming any sibling explicitly, so the boundary with 'launch' or 'routine' must be inferred.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the enumerated step catalog makes it obvious this is the general UI-interaction executor, but there is no statement of when to prefer it over launch, routine, or screenshot, and no when-not guidance. The single note that 'sensitive steps may ask the user first' is a behavior warning, not a usage rule. An agent can infer the scope but is given no routing logic.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools